{
"openapi": "3.0.1",
"info": {
"title": "Bulk Image Downloader: 22-Field Metadata, SHA-256 & ZIP",
"description": "Download every image from any webpage or direct image URL. Smart srcset picks the highest-resolution variant. 22 metadata fields per image: width, height, format, SHA-256, dedup flag, EXIF, provenance. ZIP and S3 outputs, webhooks, MCP-ready. $2.00 per 1k.",
"version": "0.1",
"x-build-id": "Va0iPAKefLSr4KEdm"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/getascraper~bulk-image-downloader/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-getascraper-bulk-image-downloader",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/getascraper~bulk-image-downloader/runs": {
"post": {
"operationId": "runs-sync-getascraper-bulk-image-downloader",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/getascraper~bulk-image-downloader/run-sync": {
"post": {
"operationId": "run-sync-getascraper-bulk-image-downloader",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
}
},
"components": {
"schemas": {
"inputSchema": {
"type": "object",
"required": [
"urls"
],
"properties": {
"urls": {
"title": "URLs to Process",
"type": "array",
"description": "List of URLs. Each can be a webpage (the Actor discovers all images on the page via HTML/srcset/og:image/twitter:image) or a direct image URL. Mixed lists allowed.",
"default": [
{
"url": "https://apify.com"
},
{
"url": "https://picsum.photos/800/600.jpg"
}
],
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"mode": {
"title": "URL Mode",
"enum": [
"auto",
"page",
"direct"
],
"type": "string",
"description": "'auto' detects by URL extension, 'page' forces HTML parsing, 'direct' treats every URL as an image.",
"default": "auto"
},
"includeSrcset": {
"title": "Include srcset / picture",
"type": "boolean",
"description": "Discover images from ![]()
, , and lazy-loaded data-src/data-srcset attributes. Picks the highest-resolution variant by default.",
"default": true
},
"includeOgTags": {
"title": "Include og:image / twitter:image",
"type": "boolean",
"description": "Discover Open Graph and Twitter Card images from page tags. Often the best cover image.",
"default": true
},
"minWidth": {
"title": "Min Width (px)",
"minimum": 0,
"maximum": 10000,
"type": "integer",
"description": "Skip images narrower than this. 0 = no minimum. Filters tracking pixels and thumbnails.",
"default": 0
},
"minHeight": {
"title": "Min Height (px)",
"minimum": 0,
"maximum": 10000,
"type": "integer",
"description": "Skip images shorter than this. 0 = no minimum.",
"default": 0
},
"minSizeBytes": {
"title": "Min Size (bytes)",
"minimum": 0,
"maximum": 10485760,
"type": "integer",
"description": "Skip images smaller than this. Filters tracking pixels and 1x1 placeholders. 0 = no minimum.",
"default": 0
},
"maxImagesPerUrl": {
"title": "Max Images per URL",
"minimum": 1,
"maximum": 10000,
"type": "integer",
"description": "Safety cap on images discovered per source URL. Prevents runaway runs on heavy pages.",
"default": 1000
},
"maxUrls": {
"title": "Max URLs to Process",
"minimum": 1,
"maximum": 100000,
"type": "integer",
"description": "Cap on total URLs processed.",
"default": 10000
},
"dedupByHash": {
"title": "Deduplicate by Content Hash",
"type": "boolean",
"description": "Compute SHA-256 of each image body and skip duplicates. Reports is_duplicate=true on the dataset.",
"default": true
},
"stripExif": {
"title": "Strip EXIF Metadata (JPEG)",
"type": "boolean",
"description": "Re-encode JPEGs without EXIF (camera model, GPS, timestamps). Privacy-friendly. Slightly lossy.",
"default": false
},
"convertFormat": {
"title": "Format Conversion",
"enum": [
"none",
"webp-to-png",
"png-to-jpg"
],
"type": "string",
"description": "Optional format conversion. webp-to-png is the most common (broader compatibility).",
"default": "none"
},
"filenamePattern": {
"title": "Filename Pattern",
"type": "string",
"description": "Templated filename. Tokens: {slug} (sanitized URL slug), {hash} (SHA-256 prefix), {ext} (extension), {idx} (index), {source} (source domain).",
"default": "{slug}-{hash}.{ext}"
},
"outputFormat": {
"title": "Output Format",
"type": "array",
"description": "Always emits the structured dataset. Optionally also: ZIP archive (single or per-URL), KV store binaries, S3 upload, or webhook on completion. Valid values: dataset, kv-store, zip, zipPerUrl, s3, webhook.",
"default": [
"dataset",
"kv-store"
],
"items": {
"type": "string"
}
},
"s3Bucket": {
"title": "S3 Bucket Name",
"type": "string",
"description": "Required when outputFormat includes 's3'. Use AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_REGION env vars (set via Apify Secrets).",
"default": ""
},
"webhookUrl": {
"title": "Webhook URL",
"type": "string",
"description": "POST a completion event with the run summary to this URL on run completion.",
"default": ""
},
"maxConcurrency": {
"title": "Max Concurrency",
"minimum": 1,
"maximum": 50,
"type": "integer",
"description": "Max parallel image downloads. Default 10.",
"default": 10
},
"downloadTimeoutMs": {
"title": "Download Timeout (ms)",
"minimum": 1000,
"maximum": 120000,
"type": "integer",
"description": "Per-image fetch timeout in milliseconds.",
"default": 15000
},
"imageCheckMaxRetries": {
"title": "Max Retries per Image",
"minimum": 0,
"maximum": 10,
"type": "integer",
"description": "Retries for failed image downloads (5xx, timeouts, transient network errors).",
"default": 3
},
"proxyConfiguration": {
"title": "Proxy Configuration",
"type": "object",
"description": "OPTIONAL. Default is no proxy. Set residential proxy if source sites are hotlink-protected or geo-fenced.",
"default": {
"useApifyProxy": false
}
},
"failFast": {
"title": "Fail Fast",
"type": "boolean",
"description": "Stop the run on the first error. Default false (continue and report per-image errors).",
"default": false
},
"debugLogging": {
"title": "Verbose Debug Logs",
"type": "boolean",
"description": "Print per-image tracing tags (FETCH, PARSE, HASH, WRITE) to run logs.",
"default": false
}
}
},
"runsResponseSchema": {
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"actId": {
"type": "string"
},
"userId": {
"type": "string"
},
"startedAt": {
"type": "string",
"format": "date-time",
"example": "2025-01-08T00:00:00.000Z"
},
"finishedAt": {
"type": "string",
"format": "date-time",
"example": "2025-01-08T00:00:00.000Z"
},
"status": {
"type": "string",
"example": "READY"
},
"meta": {
"type": "object",
"properties": {
"origin": {
"type": "string",
"example": "API"
},
"userAgent": {
"type": "string"
}
}
},
"stats": {
"type": "object",
"properties": {
"inputBodyLen": {
"type": "integer",
"example": 2000
},
"rebootCount": {
"type": "integer",
"example": 0
},
"restartCount": {
"type": "integer",
"example": 0
},
"resurrectCount": {
"type": "integer",
"example": 0
},
"computeUnits": {
"type": "integer",
"example": 0
}
}
},
"options": {
"type": "object",
"properties": {
"build": {
"type": "string",
"example": "latest"
},
"timeoutSecs": {
"type": "integer",
"example": 300
},
"memoryMbytes": {
"type": "integer",
"example": 1024
},
"diskMbytes": {
"type": "integer",
"example": 2048
}
}
},
"buildId": {
"type": "string"
},
"defaultKeyValueStoreId": {
"type": "string"
},
"defaultDatasetId": {
"type": "string"
},
"defaultRequestQueueId": {
"type": "string"
},
"buildNumber": {
"type": "string",
"example": "1.0.0"
},
"containerUrl": {
"type": "string"
},
"usage": {
"type": "object",
"properties": {
"ACTOR_COMPUTE_UNITS": {
"type": "integer",
"example": 0
},
"DATASET_READS": {
"type": "integer",
"example": 0
},
"DATASET_WRITES": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_READS": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_WRITES": {
"type": "integer",
"example": 1
},
"KEY_VALUE_STORE_LISTS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_READS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_WRITES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_INTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_EXTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_SERPS": {
"type": "integer",
"example": 0
}
}
},
"usageTotalUsd": {
"type": "number",
"example": 0.00005
},
"usageUsd": {
"type": "object",
"properties": {
"ACTOR_COMPUTE_UNITS": {
"type": "integer",
"example": 0
},
"DATASET_READS": {
"type": "integer",
"example": 0
},
"DATASET_WRITES": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_READS": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_WRITES": {
"type": "number",
"example": 0.00005
},
"KEY_VALUE_STORE_LISTS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_READS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_WRITES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_INTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_EXTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_SERPS": {
"type": "integer",
"example": 0
}
}
}
}
}
}
}
}
}
}